A Survey of the State-of-the-Art Reinforcement Learning-Based Techniques for Autonomous Vehicle Trajectory Prediction

Autonomous Vehicles (AVs) have emerged as a promising solution by replacing human drivers with advanced computer-aided decision-making systems. However, for AVs to effectively navigate the road, they must possess the capability to predict the future trajectories of nearby traffic participants, similar to the predictive driving abilities of human drivers. Reinforcement Learning (RL) has emerged as a promising approach for learning complex decision-making policies in dynamic environments. This survey explores the application of RL approaches in trajectory prediction, focusing on inverse reinforcement learning, deep reinforcement learning, and imitation learning. It provides an in-depth analysis of the underlying principles, algorithms, and architectures employed in these methods, highlighting their respective strengths and limitations. Moreover, the survey addresses the current challenges in the field and presents potential future research directions, offering valuable insights to readers.